data_accessor_splitting_memARFF.hpp

Go to the documentation of this file.

#ifndef FSTDATAACCESSORSPLITTINGMEMARFF_H
#define FSTDATAACCESSORSPLITTINGMEMARFF_H
 /* 
=========================================================================
Copyright and license:
  * FST4 software (with the exception of any bundled or externally linked
    third-party components) is Copyright (C) 2000-present Institute of
    Information Theory and Automation of the Czech Academy of Sciences (UTIA).
  * FST4 is free software: you can redistribute it and/or modify it under
    the terms of the GNU Affero General Public License as published by the
    Free Software Foundation, version 3. The full text of the license is in
    the file LICENSE in the distribution root and at
    https://www.gnu.org/licenses/agpl-3.0.html.
  * FST4 is distributed in the hope that it will be useful, but WITHOUT ANY
    WARRANTY; without even the implied warranty of MERCHANTABILITY or
    FITNESS FOR A PARTICULAR PURPOSE. See the GNU Affero General Public
    License for more details.
  * Closed-source use without the AGPL's copyleft obligations requires a
    commercial license from UTIA; in case of interest write to
    utia@utia.cas.cz. LICENSING.md in the distribution root explains both
    options, the contributor license agreement that every contribution
    requires, and the contacts (technical questions and pull requests:
    somol@utia.cas.cz, with "FST" in the subject line).
========================================================================== */
 
#include <memory>
#include <iostream>
#include <sstream>
#include <vector>
 
#include "error.hpp"
#include "global.hpp"
#include "data_accessor_splitting_mem.hpp"
#include "data_file_ARFF.hpp"
 
/*============== Template parameter type naming conventions ==============
--------- Numeric types: -------------------------------------------------
DATATYPE - data sample values - usually real numbers (but may be integers
          in text processing etc.)
REALTYPE - must be real numbers - for representing intermediate results of 
          calculations like mean, covariance etc.
IDXTYPE - index values for enumeration of data samples - (nonnegative) integers, 
          extent depends on numbers of samples in data
DIMTYPE - index values for enumeration of features (dimensions), or classes (not 
          class sizes) - (nonnegative) integers, usually lower extent than IDXTYPE, 
          but be aware of expressions like _classes*_features*_features ! 
          in linearized representations of feature matrices for all classes
BINTYPE - feature selection marker type - represents ca. <10 different feature 
          states (selected, deselected, sel./desel. temporarily 1st nested loop, 2nd...)
RETURNTYPE - criterion value: real value, but may be extended in future to support 
          multiple values 
--------- Class types: ---------------------------------------------------
SUBSET       - class of class type Subset 
CLASSIFIER   - class implementing interface defined in abstract class Classifier 
EVALUATOR    - class implementing interface defined in abstract class Sequential_Step 
DISTANCE     - class implementing interface defined in abstract class Distance 
DATAACCESSOR - class implementing interface defined in abstract class Data_Accessor 
INTERVALCONTAINER - class of class type Data_Intervaller 
CONTAINER    - STL container of class type Data_Interval  
========================================================================== */
 
namespace FST {

template<typename DATATYPE, typename IDXTYPE, class INTERVALCONTAINER>
class Data_Accessor_Splitting_MemARFF : public Clonable_Impl<Data_Accessor_Splitting_MemARFF<DATATYPE,IDXTYPE,INTERVALCONTAINER>,Data_Accessor_Splitting_Mem<DATATYPE,IDXTYPE,INTERVALCONTAINER>,CLONE_INHERIT,CLONE_WEAK_SHARING,CLONE_INHERIT>
{
        // NOTE: the calling convention is the same for the inner and the outer CV loop -- both call just
        //   get*Split, get*Block, get*Pattern -- and which of them a call refers to is selected beforehand
        //   with the inherited setSplittingDepth()
        public:
                typedef Data_Accessor_Splitting_Mem<DATATYPE,IDXTYPE,INTERVALCONTAINER> DASM; 
                typedef Clonable_Impl<Data_Accessor_Splitting_MemARFF,DASM,CLONE_INHERIT,CLONE_WEAK_SHARING,CLONE_INHERIT> parent_impl;
                typedef std::shared_ptr<Data_Scaler<DATATYPE> > PScaler; 
                typedef typename DASM::PSplitters PSplitters; 
                Data_Accessor_Splitting_MemARFF(const std::string _filename, const PSplitters _dsp, const PScaler _dsc) : parent_impl(_filename, _dsp, _dsc) {notify("Data_Accessor_Splitting_MemARFF constructor.");}
                virtual ~Data_Accessor_Splitting_MemARFF(){notify("Data_Accessor_Splitting_MemARFF destructor.");}
 
                virtual std::ostream& print(std::ostream& os) const override;
        protected:
                friend parent_impl; 
                Data_Accessor_Splitting_MemARFF(const Data_Accessor_Splitting_MemARFF &damt, int x) : parent_impl(damt, x), clsCount(damt.clsCount), featureCount(damt.featureCount), clsSize(damt.clsSize) {};
        protected:
                std::unique_ptr<Data_File_ARFF> ARFFFile;  
 
                unsigned int clsCount;      
                unsigned int featureCount;  
                std::shared_ptr<IDXTYPE> clsSize;  
 
                virtual void initial_data_read() override ;    
                virtual void initial_file_prepare() override; 
 
    public:
                virtual unsigned int file_getNoOfClasses() const override {return clsCount; } 
                virtual unsigned int file_getNoOfFeatures() const override {return featureCount; } 
                virtual IDXTYPE file_getClassSize(unsigned int cls) const override {return clsSize.get()[cls]; } 
};
 
template<typename DATATYPE, typename IDXTYPE, class INTERVALCONTAINER>
void Data_Accessor_Splitting_MemARFF<DATATYPE,IDXTYPE,INTERVALCONTAINER>::initial_file_prepare()
{
        if(Clonable::is_sharing_clone()) throw fst_error("Data_Accessor_Splitting_MemARFF()::initial_file_prepare() called from shared_clone instance.");
        ARFFFile.reset(new Data_File_ARFF(this->filename));
        if(!ARFFFile->prepareFile()) // the reader has already printed the offending line/reason
                throw fst_error("ARFF file '"+this->filename+"' could not be loaded (see the reader's message above for the offending definition or data row)");
        ARFFFile->sortRecordsByClass();
        
        clsCount = ARFFFile->getNoOfClasses();
        featureCount = ARFFFile->getNoOfFeatures();
        clsSize.reset(new IDXTYPE[clsCount], std::default_delete<IDXTYPE[]>());
        for (unsigned int i=0;i<clsCount; i++) clsSize.get()[i] = ARFFFile->getClassSize(i);
}
 
template<typename DATATYPE, typename IDXTYPE, class INTERVALCONTAINER>
void Data_Accessor_Splitting_MemARFF<DATATYPE,IDXTYPE,INTERVALCONTAINER>::initial_data_read()
{
        if(Clonable::is_sharing_clone()) throw fst_error("Data_Accessor_Splitting_MemARFF()::initial_data_read() called from shared_clone instance.");
        {std::ostringstream sos; sos << "Reading data to memory..."; syncout::print(std::cout,sos);}
        IDXTYPE idx=0;
        for(unsigned int p=0;p<ARFFFile->getTotalSize();p++) 
        {
                for(unsigned int f=0;f<ARFFFile->getNoOfFeatures();f++) {
                        this->data.get()[idx++]=(DATATYPE) ARFFFile->getFeatureValue(p,f);
                }
        }
        ARFFFile.reset();
        {std::ostringstream sos; sos << "done."<<std::endl; syncout::print(std::cout,sos);}
}
 
 
 
template<typename DATATYPE, typename IDXTYPE, class INTERVALCONTAINER>
std::ostream& Data_Accessor_Splitting_MemARFF<DATATYPE,IDXTYPE,INTERVALCONTAINER>::print(std::ostream& os) const 
{
        DASM::print(os); 
        os << std::endl << "Data_Accessor_Splitting_MemARFF()";
        return os;
}
        
} // namespace
#endif // FSTDATAACCESSORSPLITTINGMEMARFF_H ///:~